Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b11ab3fbbfff5b25c753c32c7ee5820758c1b6245d80ff71552c1aeda494445
+oid sha256:acb38c4bdaf385e847c23f6426861762fc30c396ffe396929419ea17e2f54a7b
 size 1101572914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd5c570e8e8139c52ffe81c5c75ce52078baa20f08328126f4d09778514a25b0
+oid sha256:8045872fca2455adab861fcdd8ffebe0c1674421c3ca38a87bb2ec3128286bd5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f6891a2dad4098258cacbb534eda6cb23344f32c27a937c7da2508a5fd6662
+oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004284857314251435,
+  "epoch": 0.00856971462850287,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 5.242,
       "eval_steps_per_second": 2.622,
       "step": 25
+    },
+    {
+      "epoch": 0.004456251606821493,
+      "grad_norm": NaN,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0046276458993915505,
+      "grad_norm": NaN,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.004799040191961607,
+      "grad_norm": NaN,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.004970434484531665,
+      "grad_norm": NaN,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.005141828777101723,
+      "grad_norm": NaN,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00531322306967178,
+      "grad_norm": NaN,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.005484617362241837,
+      "grad_norm": NaN,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.005656011654811895,
+      "grad_norm": NaN,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.005827405947381952,
+      "grad_norm": NaN,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.00599880023995201,
+      "grad_norm": NaN,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.006170194532522067,
+      "grad_norm": NaN,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.006341588825092124,
+      "grad_norm": NaN,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.006512983117662182,
+      "grad_norm": NaN,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.00668437741023224,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0068557717028022965,
+      "grad_norm": NaN,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.007027165995372354,
+      "grad_norm": NaN,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.007198560287942412,
+      "grad_norm": NaN,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0073699545805124686,
+      "grad_norm": NaN,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.007541348873082526,
+      "grad_norm": NaN,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.007712743165652584,
+      "grad_norm": NaN,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.007884137458222642,
+      "grad_norm": NaN,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.008055531750792698,
+      "grad_norm": NaN,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.008226926043362757,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.008398320335932814,
+      "grad_norm": NaN,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.00856971462850287,
+      "grad_norm": NaN,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.00856971462850287,
+      "eval_loss": NaN,
+      "eval_runtime": 468.5593,
+      "eval_samples_per_second": 5.244,
+      "eval_steps_per_second": 2.623,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.47236554768384e+16,
+  "total_flos": 6.94473109536768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null